cs.LG（2025-12-22）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
1 CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal CARE：面向可验证多模态推理，通过对比锚定反射改进失败案例学习。 reinforcement learning multimodal
2 Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling 提出基于Lag算子的结构化状态空间建模几何框架，简化SSM设计。 Mamba SSM state space model
3 Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies 提出自底向上策略优化(BuPO)，通过优化LLM内部策略提升复杂推理能力。 reinforcement learning large language model ✅
4 LacaDM: A Latent Causal Diffusion Model for Multiobjective Reinforcement Learning 提出LacaDM，通过潜在因果扩散模型提升多目标强化学习适应性 reinforcement learning
5 Real-Time Streamable Generative Speech Restoration with Flow Matching 提出Stream.FM：一种实时流式生成语音恢复Flow Matching模型，延迟低至48ms。 flow matching
6 Scaling Online Distributionally Robust Reinforcement Learning: Sample-Efficient Guarantees with General Function Approximation 提出在线分布鲁棒强化学习算法，解决训练与部署环境不匹配问题。 reinforcement learning
7 Learning Through Little Eyes: Attribute Discrimination Beyond Objects 通过婴儿视角学习：探索超越物体的属性辨别能力 contrastive learning egocentric
8 Cluster-Based Generalized Additive Models Informed by Random Fourier Features 提出基于随机傅里叶特征的聚类广义加性模型，提升可解释回归任务的预测性能。 predictive model representation learning
9 Interpretable Hybrid Deep Q-Learning Framework for IoT-Based Food Spoilage Prediction with Synthetic Data Generation and Hardware Validation 提出一种可解释的混合深度Q学习框架，用于物联网食品腐败预测，并进行硬件验证。 reinforcement learning deep reinforcement learning
10 Explicit and Non-asymptotic Query Complexities of Rank-Based Zeroth-order Algorithm on Stochastic Smooth Functions 提出基于排序的零阶算法，解决随机光滑函数优化问题，达到最优查询效率。 reinforcement learning preference learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
11 R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression R-GenIMA：融合神经影像与遗传信息的Alzheimer病进展可解释多模态AI模型 large language model multimodal
12 OmniMER: Indonesian Multimodal Emotion Recognition via Auxiliary-Enhanced LLM Adaptation 提出OmniMER以解决印尼多模态情感识别问题 multimodal ✅
13 HyperLoad: A Cross-Modality Enhanced Large Language Model-Based Framework for Green Data Center Cooling Load Prediction HyperLoad：基于跨模态增强大语言模型的绿色数据中心冷却负荷预测框架 large language model
14 MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning MixKVQ：面向长文本推理的查询感知混合精度KV缓存量化 large language model chain-of-thought
15 Brain-Grounded Axes for Reading and Steering LLM States 提出基于人脑活动的LLM状态解读与操控方法，实现神经生理学层面可控性。 large language model
16 Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement MACLA：通过贝叶斯选择和对比精炼学习LLM Agent的分层程序记忆 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页